Using Network Alignment to Identify Conserved Consumer Behaviour Modelling Constructs

Mathieson, L; de Vries, NJ; Moscato, P

Using Network Alignment to Identify Conserved Consumer Behaviour Modelling Constructs

Mathieson, L

de Vries, NJ Moscato, P

Permalink

Publisher:: Springer International Publishing
Publication Type:: Chapter
Citation:: Business and Consumer Analytics: New Ideas, 2019, pp. 513 - 541
Issue Date:: 2019-01-01

Closed Access

	Filename	Description	Size
	Pages from 2019_Book_BusinessAndConsumerAnalyticsNe.pdf	Published version	21.88 MB	Adobe PDF	View/Open

Copyright Clearance Process

Recently Added
In Progress
Closed Access

This item is closed access and not available.

Full metadata record

Field	Value	Language
dc.contributor.author	Mathieson, L https://orcid.org/0000-0001-6470-2296	en_US
dc.contributor.author	de Vries, NJ	en_US
dc.contributor.author	Moscato, P	en_US
dc.contributor.editor	Moscato, P	en_US
dc.contributor.editor	de Vries, NJ	en_US
dc.date.accessioned	2020-04-19T08:02:11Z
dc.date.available	2020-04-19T08:02:11Z
dc.date.issued	2019-01-01	en_US
dc.identifier.citation	Business and Consumer Analytics: New Ideas, 2019, pp. 513 - 541	en_US
dc.identifier.isbn	978-3-030-06221-7	en_US
dc.identifier.uri	http://hdl.handle.net/10453/140085
dc.description.abstract	Extracting topological information from networks is a central problem in many fields including business analytics. With the increase in large-scale datasets, effectively comparing similarities and differences between networks is impossible without automation. In some cases, computational search of simple subgraphs is used to understand the structure of a network. These approaches, however, miss the “global picture” of network similarity. Here we examine the Network Alignment problem, in which we look for a mapping between vertex sets of two networks preserving topological information. Elsewhere, we showed that data analytics problems are often of varied computational complexity. We prove that this problem is W[1]-complete for several parameterizations. Since we expect large instances in the data analytics field, our result indicates that this problem is a prime candidate for metaheuristic approaches as it will be hard in practice to solve exact methods. We develop a memetic algorithm and demonstrate the effectiveness of the Network Alignment problem as a tool for discovering structural information through an application in the area of consumer behaviour modelling. We believe this to be the first demonstration of such an approach in the social sciences and in particular a consumer analytics application.	en_US
dc.publisher	Springer International Publishing	en_US
dc.relation.ispartof	Business and Consumer Analytics: New Ideas	en_US
dc.relation.isbasedon	10.1007/978-3-030-06222-4_12	en_US
dc.rights	info:eu-repo/semantics/closedAccess
dc.title	Using Network Alignment to Identify Conserved Consumer Behaviour Modelling Constructs	en_US
dc.type	Chapter
pubs.embargo.period	Not known	en_US
pubs.organisational-group	/University of Technology Sydney
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology/School of Computer Science
utslib.copyright.status	closed_access	*
pubs.consider-herdc	false	en_US
pubs.publication-status	Published	en_US

Abstract:

Extracting topological information from networks is a central problem in many fields including business analytics. With the increase in large-scale datasets, effectively comparing similarities and differences between networks is impossible without automation. In some cases, computational search of simple subgraphs is used to understand the structure of a network. These approaches, however, miss the “global picture” of network similarity. Here we examine the Network Alignment problem, in which we look for a mapping between vertex sets of two networks preserving topological information. Elsewhere, we showed that data analytics problems are often of varied computational complexity. We prove that this problem is W[1]-complete for several parameterizations. Since we expect large instances in the data analytics field, our result indicates that this problem is a prime candidate for metaheuristic approaches as it will be hard in practice to solve exact methods. We develop a memetic algorithm and demonstrate the effectiveness of the Network Alignment problem as a tool for discovering structural information through an application in the area of consumer behaviour modelling. We believe this to be the first demonstration of such an approach in the social sciences and in particular a consumer analytics application.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/140085